dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python

Authors: Hubert Baniecki, Wojciech Kretowicz, Piotr Piątyszek, Jakub Wiśniewski, Przemysław Biecek

JMLR 2021 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical To facilitate the responsible development of machine learning models, we introduce dalex, a Python package which implements a model-agnostic interface for interactive explainability and fairness. It adopts the design crafted through the development of various tools for explainable machine learning; thus, it aims at the unification of existing solutions. This library s source code and documentation are available under open license at https://python.drwhy.ai.
Researcher Affiliation Collaboration 1Faculty of Mathematics and Information Science, Warsaw University of Technology, Poland 2Samsung Research & Development Institute, Poland
Pseudocode No The paper describes the architecture and features of the dalex Python package, including illustrative code snippets for its usage, but it does not contain any structured pseudocode blocks or algorithms describing a specific method implemented or developed within the paper.
Open Source Code Yes This library s source code and documentation are available under open license at https://python.drwhy.ai.
Open Datasets No The paper introduces a software package and its functionalities but does not conduct experiments on specific datasets or provide access information for any open datasets used in its own research.
Dataset Splits No The paper does not describe any experiments that would require dataset splits, as its focus is on introducing a software package rather than reporting empirical results on specific datasets.
Hardware Specification No The paper describes a software package and its capabilities but does not mention any specific hardware (like GPU or CPU models) used for experiments.
Software Dependencies No The paper mentions various Python libraries that dalex interacts with or builds upon, such as 'scikit-learn', 'tensorflow', 'xgboost', 'numpy', 'pandas', and 'plotly', and states 'version 1.3 for Python 3.9' for dalex itself. However, it does not provide specific version numbers for these external software dependencies, which are required for full reproducibility.
Experiment Setup No The paper introduces a software package and its architecture; it does not describe any specific experiments, hyperparameters, or training configurations.